How to Use the Botsonic MCP in Pydantic AI

Q: How do I set up Botsonic with Pydantic AI?

Install pydantic-ai-slimmcp and use the MCPToolset constructor with your Vinkius HTTP endpoint. Pass this MCP toolset directly into your agent's toolsets list to begin.

Q: Does the Botsonic MCP Server support streaming responses in Pydantic AI?

Yes. You can use the SSE transport option in your MCPToolset setup. This allows your agent to handle real-time events and update bot configurations without blocking your main execution loop.

Q: Can I audit my Botsonic knowledge base with Pydantic AI?

Yes. Your agent can call listknowledgebase to pull all active training sources. The framework validates the URLs and source metadata, letting you easily spot and prune dead links.

Type-safe support automation. Connect Pydantic AI to Botsonic to validate every bot update, lead, and conversation at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Botsonic MCP to Pydantic AI

Create your Vinkius account to connect Botsonic to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Botsonic with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Botsonic MCP Server Management

This MCP Server lets you control your support bots with strict runtime validation using tools like `create_bot` and `update_bot`. Every response from the API is validated against strict Pydantic models, preventing corrupt configurations from breaking your production environment. If the API returns unexpected fields, your agent raises a clear validation error immediately instead of failing silently. This guarantees that your bot settings remain consistent and error-free.

Validated Lead and Analytics Parsing

Your agent uses `list_leads` and `get_bot_analytics` to pull structured marketing and performance data from your support widgets. Pydantic AI guarantees that every email, phone number, and metric matches your exact schema before it hits your database. This prevents malformed lead data or broken analytics counts from polluting your CRM. You get clean, type-safe data pipelines directly from your automated support channels.

Strict Conversation Auditing

Use `get_conversation` and `list_conversations` to monitor customer chats with guaranteed data structures. Your agent can safely inspect chat histories to flag bad answers or extract user issues without risking parsing crashes. You can also use `send_message` to programmatically test your bots. The agent sends test queries, validates the bot's response format, and alerts your team if the bot goes off-script.

Setup guide

Set up Botsonic MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "botsonic-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Botsonic tools.",
)

result = await agent.run("List recent Botsonic transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Botsonic. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Botsonic now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Botsonic MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and use the `MCPToolset` constructor with your Vinkius HTTP endpoint. Pass this MCP toolset directly into your agent's `toolsets` list to begin.

Yes. You can use the SSE transport option in your `MCPToolset` setup. This allows your agent to handle real-time events and update bot configurations without blocking your main execution loop.

The framework catches the error and raises a validation or execution exception. You can handle this gracefully in your Python code, ensuring your application never processes half-baked support data.

Yes. Your agent can call `list_knowledge_base` to pull all active training sources. The framework validates the URLs and source metadata, letting you easily spot and prune dead links.

Vinkius runs this MCP Server inside an isolated V8 sandbox. All conversation logs, lead details, and API tokens are processed in memory and immediately discarded, ensuring customer chat histories are never stored or logged on the proxy layer.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript